xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-26 08:09:37 +08:00
Code Issues Packages Projects Releases Wiki Activity
6,075 Commits 155 Branches 89 Tags
Commit Graph

4114 Commits

Author SHA1 Message Date
Nick Hill
df6f3ce883
[Core] Remove prompt string from engine core data structures (#17214) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-04-25 23:41:05 -07:00
Woosuk Kwon
513f074766
[CI/test] Fix Eagle Correctness Test (#17209) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-04-25 23:40:36 -07:00
Nick Hill
b07bf83c7d
[BugFix] Avoid race conditions in zero-copy tensor transmission (#17203) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-04-26 06:00:07 +00:00
Zijing Liu
53e8cf53a4
[V1][Metrics] Allow V1 AsyncLLM to use custom logger (#14661) 
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
 2025-04-25 22:05:40 -07:00
Charlie Fu
54271bb766
[ROCm][Misc] Follow-ups for Skinny Gemms on ROCm. (#17011) 
Signed-off-by: charlifu <charlifu@amd.com>
 2025-04-25 22:05:10 -07:00
Shu Wang
9e96f56efb
Allocate kv_cache with stride order (#16605) 
Signed-off-by: shuw <shuw@nvidia.com>
 2025-04-25 22:03:31 -07:00
Woosuk Kwon
b278911229
[Minor][Models] Fix Return Types of Llama & Eagle (#17220) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-04-25 21:54:47 -07:00
Woosuk Kwon
1cf0719ebd
[Minor][Spec Decode] Add use_eagle to SpeculativeConfig (#17213) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-04-25 21:08:15 -07:00
James Wu
a6e72e1e4f
[Bugfix] [pytorch] Patch AOTAutogradCache._get_shape_env (#17142) 
Signed-off-by: James Wu <jjwu@meta.com>
 2025-04-26 11:28:20 +08:00
Yihua Cheng
5e83a7277f
[v1] [P/D] Adding LMCache KV connector for v1 (#16625) 2025-04-26 03:03:38 +00:00
rasmith
68af5f6c5c
[AMD][FP8][BugFix] Remove V1 check in arg_utils.py for FP8 since it is not necessary (#17215) 
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
 2025-04-25 19:55:05 -07:00
Chen Zhang
8de2901fea
[Bugfix] gemma[2,3] interleaved attention when sliding window is disabled (#17180) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-04-25 19:53:51 -07:00
Benjamin Chislett
a0e619e62a
[V1][Spec Decode] EAGLE-3 Support (#16937) 
Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Co-authored-by: Bryan Lu <yuzhelu@amazon.com>
 2025-04-25 15:43:07 -07:00
Nick Hill
70116459c3
[BugFix][Frontend] Fix LLM.chat() tokenization (#16081) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-04-25 22:20:05 +00:00
Christian Heimes
65e262b93b
Fix Python packaging edge cases (#17159) 
Signed-off-by: Christian Heimes <christian@python.org>
 2025-04-26 06:15:07 +08:00
Daniel Li
48cb2109b6
[V1] Move usage stats to worker and start logging TPU hardware (#16211) 2025-04-25 14:06:01 -06:00
Russell Bryant
a5450f11c9
[Security] Use safe serialization and fix zmq setup for mooncake pipe (#17192) 
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
Co-authored-by: Shangming Cai <caishangming@linux.alibaba.com>
 2025-04-25 16:53:23 +00:00
Harry Mellor
423e9f1cbe
Use Transformers helper get_text_config() instead of checking for text_config (#17105) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-25 08:47:35 -07:00
Jasmond L
d5615af9ae
[Bugfix] Fix Mistral ChatCompletionRequest Body Exception (#16769) 
Signed-off-by: Jasmond Loh <Jasmond.Loh@hotmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2025-04-25 07:26:30 -07:00
Cyrus Leung
19dcc02a72
[Bugfix] Fix mistral model tests (#17181) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-04-25 06:03:34 -07:00
Alex Brooks
7feae92c1f
[Doc] Move todo out of beam search docstring (#17183) 
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
 2025-04-25 04:44:58 -07:00
Lu Fang
fc966e9cc6
Only turn on FastIncrementalDetokenizer when tokenizers >= 0.21.1 (#17158) 2025-04-25 17:10:32 +08:00
rasmith
a41351f363
[Quantization][FP8] Add support for FP8 models with input_scale for output projection and QK quantization (#15734) 
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
 2025-04-25 00:45:02 -07:00
Sangyeon Cho
6aae216b4e
[Bugfix] remove fallback in guided_json (int range, patterns) (#16725) 
Signed-off-by: csy1204 <josang1204@gmail.com>
Co-authored-by: 조상연[플레이스 AI] <sang-yeon.cho@navercorp.com>
 2025-04-25 06:54:43 +00:00
yexin(叶鑫)
b22980a1dc
[Perf]Optimize rotary_emb implementation to use Triton operator for improved inference performance (#16457) 
Signed-off-by: cynthieye <yexin93@qq.com>
Co-authored-by: MagnetoWang <magnetowang@outlook.com>
 2025-04-25 14:52:28 +08:00
Mengqing Cao
2f54045508
[Bugfix][Misc] Use TritonPlaceholderModule to defensively import triton (#15099) 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
 2025-04-24 22:51:02 -07:00
Lifu Huang
5aa6efb9a5
[Misc] Clean up redundant code in uniproc_executor.py (#16762) 
Signed-off-by: Lifu Huang <lifu.hlf@gmail.com>
 2025-04-24 22:49:30 -07:00
Harry Mellor
6ca0234478
Move missed SchedulerConfig args into scheduler config group in EngineArgs (#17131) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-24 22:48:53 -07:00
Zaida Zhou
69bff9bc89
fix float16 support for kimi-vl (#17156) 
Co-authored-by: zhouzaida <zhouzaida@msh.team>
 2025-04-24 20:16:32 -07:00
vllmellm
eef364723c
[FEAT] [ROCm]: AITER Fused MOE V1 Support (#16752) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-04-25 11:06:50 +08:00
jglaser
0d6e187e88
Use custom address for listening socket (#15988) 
Signed-off-by: Jens Glaser <glaserj@ornl.gov>
 2025-04-25 01:57:16 +00:00
Michael Goin
9420a1fc30
Better error message for missing mistral params.json (#17132) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-04-24 23:43:08 +00:00
Maximilien de Bayser
05e1fbfc52
Add chat template for Llama 4 models (#16428) 
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
 2025-04-24 20:19:36 +00:00
Yinghai Lu
fe92176321
Add collective_rpc to llm engine (#16999) 
Signed-off-by: Yinghai Lu <yinghai@thinkingmachines.ai>
 2025-04-24 20:16:52 +00:00
Harry Mellor
0fa939e2d1
Improve configs - LoRAConfig + PromptAdapterConfig (#16980) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-24 10:29:34 -07:00
Mark McLoughlin
340d7b1b21
[V1][Spec Decoding] Add num_drafts and num_accepted_tokens_per_position metrics (#16665) 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
 2025-04-24 08:57:40 -07:00
wang.yuqi
67309a1cb5
[Frontend] Using matryoshka_dimensions control the allowed output dimensions. (#16970) 2025-04-24 07:06:28 -07:00
Shanshan Shen
b724afe343
[V1][Structured Output] Clear xgrammar compiler object when engine core shut down to avoid nanobind leaked warning (#16954) 
Signed-off-by: shen-shanshan <467638484@qq.com>
 2025-04-24 06:15:03 -07:00
Harry Mellor
21f4f1c9a4
Improve static type checking in LoRAModelRunnerMixin (#17104) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-24 06:14:47 -07:00
Isotr0py
b0c1f6202d
[Misc] Remove OLMo2 config copy (#17066) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-04-24 06:14:32 -07:00
Rui Qiao
c0dfd97519
[V1][PP] Optimization: continue scheduling prefill chunks (#17080) 
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
 2025-04-24 05:27:08 -07:00
Harry Mellor
0a05ed57e6
Simplify TokenizerGroup (#16790) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-24 04:43:56 -07:00
Woosuk Kwon
b411418ff0
[Chore] Remove Sampler from Model Code (#17084) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-04-24 02:49:33 -07:00
张宇
6167c0e5d2
[Bugfix][Core] add seq_id_to_seq_group clearing to avoid memory leak when s… (#16472) 
Signed-off-by: 开哲 <kaizhe.zy@alibaba-inc.com>
Co-authored-by: 开哲 <kaizhe.zy@alibaba-inc.com>
 2025-04-24 11:25:37 +08:00
Areeb Syed
ed2e464653
Addendum Fix to support FIPS enabled machines with MD5 hashing (#17043) 
Signed-off-by: sydarb <areebsyed237@gmail.com>
 2025-04-23 19:55:00 -07:00
Harry Mellor
2c8ed8ee48
More informative error when using Transformers backend (#16988) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-23 19:54:03 -07:00
Michael Goin
ed50f46641
[Bugfix] Enable V1 usage stats (#16986) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
 2025-04-23 19:54:00 -07:00
Woosuk Kwon
46e678bcff
[Minor] Use larger batch sizes for A100/B100/B200/MI300x (#17073) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-04-23 19:18:59 -07:00
Chen Xia
6b2427f995
[Quantization]add prefix for commandA quantized model (#17017) 2025-04-23 17:32:40 -07:00
Woosuk Kwon
41fb013d29
[V1][Spec Decode] Always use argmax for sampling draft tokens (#16899) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-04-23 14:57:43 -07:00